{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "UNK", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "PAD", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "WORD_BOUNDARY", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "UTT_BOUNDARY", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "Strip", "strip_left": true, "strip_right": true } ] }, "pre_tokenizer": { "type": "Whitespace" }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "UTT_BOUNDARY", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } } ], "pair": [ { "SpecialToken": { "id": "UTT_BOUNDARY", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "UTT_BOUNDARY", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } } ], "special_tokens": { "UTT_BOUNDARY": { "id": "UTT_BOUNDARY", "ids": [ 3 ], "tokens": [ "UTT_BOUNDARY" ] } } }, "decoder": null, "model": { "type": "WordLevel", "vocab": { "UNK": 0, "PAD": 1, "WORD_BOUNDARY": 2, "UTT_BOUNDARY": 3, "t̪ʰ": 4, "ɑ": 5, "kː": 6, "ʋ": 7, "a": 8, "ɾ": 9, "ʃ": 10, "o̞ː": 11, "ɡ": 12, "uː": 13, "d̪": 14, "eː": 15, "e̞": 16, "s": 17, "h": 18, "ʉː": 19, "tː": 20, "n̪": 21, "pː": 22, "ə": 23, "l": 24, "ɪ": 25, "b": 26, "iː": 27, "æ": 28, "j": 29, "kʰ": 30, "ʉ": 31, "ɒ̝": 32, "m": 33, "ø̞ː": 34, "f": 35, "yː": 36, "ai": 37, "pʰ": 38, "øy": 39, "ŋ": 40, "dː": 41, "œ": 42, "bː": 43, "ç": 44, "æː": 45, "ɑː": 46, "ʏ": 47, "æʉ": 48, "ʊ": 49, "ɡː": 50, "ɔy": 51, "ʂ": 52, "w": 53 }, "unk_token": "UNK" } }